2025-10-13 ノースウェスタン大学
<関連情報>
- https://news.northwestern.edu/stories/2025/10/ai-models-predict-sepsis-in-children-enable-preemptive-care
- https://jamanetwork.com/journals/jamapediatrics/article-abstract/2840033
小児早期敗血症の予測モデルの導出と検証 Derivation and Validation of Predictive Models for Early Pediatric Sepsis
Elizabeth R. Alpern, MD, MSCE; Halden F. Scott, MD, MSCS; Fran Balamuth, MD, PhD, MSCE;et al
JAMA Pediatrics Published:October 13, 2025
DOI:10.1001/jamapediatrics.2025.3892
Key Points
Question What is the predictive power of machine learning models for pediatric sepsis in the emergency department using electronic health record data to identify patients without sepsis who will develop sepsis within 48 hours?
Findings Using more than 1.6 million ED visits, models to predict Phoenix Sepsis Criteria scores were derived and validated. The gradient tree boosting models for PSC sepsis had meaningful positive likelihood ratios.
Meaning Machine learning predictive models for sepsis in the ED can identify children who have not yet developed sepsis and may be useful in future implementation work to identify children at risk.
Abstract
Importance Sepsis is a leading cause of death in children. Early recognition and treatment improve outcomes, but predictive models have not to date improved early diagnosis.
Objective To develop machine learning models to estimate the probability of developing sepsis in the subsequent 48 hours.
Design, Setting, and Participants This was a multisite registry for model derivation and validation using electronic health record (EHR) data from January 2016 through February 2020 and temporal validation from January 2021 through December 2022. The performance of machine learning algorithms was compared to predict development of sepsis and septic shock via logistic regression, specifically ridge regression and gradient tree boosting. Five health systems contributing to the Pediatric Emergency Care Applied Research Network were included. Emergency department (ED) visits for children aged 2 months or older to less than 18 years of age excluding patients with ED disposition of death or transfer, trauma diagnosis, or sepsis present during predictive features window. The TRIPOD-AI reporting guideline was followed, and data analysis was conducted from September 2023 to July 2025.
Exposures Patient and physiologic characteristics within the first 4 hours of ED care.
Main Outcomes and Measures Sepsis, defined as suspected infection with a Phoenix Sepsis Criteria (PSC) score of 2 or more or death within 48 hours of ED arrival.
Results The dataset included 1 604 422 eligible visits in the training cohort and 719 298 visits in the test cohort. Performance characteristics for the PSC sepsis prediction models were AUROC of 0.92 (95% CI, 0.92-0.93) for logistic regression and 0.94 (95% CI, 0.93-0.94) for gradient tree boosting. AUROCs for PSC shock models were 0.92 or greater. The gradient tree boosting models had positive likelihood ratios ranging from 4.67 (95% CI, 4.61-4.74) to 6.18 (95% CI, 6.08-6.28) for sepsis and from 4.16 (95% CI, 4.07-4.24) to 5.83 (95% CI, 5.67-5.99) for septic shock. Predictive features included emergency severity index, age-adjusted vital signs, and medical complexity. Assessment of model performance fairness was similar for all demographic characteristics except payor; AUROC for patients with Medicaid insurance was better than for those with commercial payers.
Conclusions and Relevance Using a large multicenter population, models were developed and validated with high AUROC to predict the future development of sepsis based on EHR data collected in the ED. The models achieved positive likelihood ratios to predict sepsis and septic shock. The results highlight the opportunity for future studies that combine EHR-based models with clinical judgment to improve prediction.
